skills.rest
andershi666
andershi666COMMUNITY
Explore all skills by this author →
GitHub

agent-tracing

Records and inspects agent execution snapshots, including messages, context, and tool calls, via CLI.

1|Updated Apr 14, 2026
Search Tags:#debugging#cli#llm#agent#trace#snapshot#context-engine
One-click install
npx skills add https://github.com/andershi666/lobehub-hr-demo --skill agent-tracing-andershi666
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-tracing
Source: https://github.com/andershi666/lobehub-hr-demo/tree/main/lobehub/.agents/skills/agent-tracing
Command: npx skills add https://github.com/andershi666/lobehub-hr-demo --skill agent-tracing-andershi666

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Agent tracing CLI for inspecting agent execution snapshots. Use when user mentions 'agent-tracing', 'trace', 'snapshot', wants to debug agent execution, inspect LLM calls, view context engine data, or analyze agent steps. Triggers on agent debugging, trace inspection, or execution analysis tasks.

Core Features & Use Cases

  • Zero-configuration local dev tool that records agent execution snapshots to disk and provides a CLI to inspect them.
  • Presents complete and partial execution data, including context engine input and final LLM payload, across steps.
  • Supports inspecting messages, tools, memory, events, and runtime context for troubleshooting.

Quick Start

Inspect the latest trace using agent-tracing to view steps, messages, context, and tools.

Frequently Asked Questions about agent-tracing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I inspect agent execution snapshots to debug LLM calls?▼

You inspect agent execution snapshots by running a local CLI that records steps, messages, runtime context, and tool calls to disk for review during development.

What is agent tracing and how does it help troubleshoot agent behavior?▼

Agent tracing is recording execution snapshots to inspect agent behavior. It helps troubleshooting by exposing complete and partial trace data, including context engine input and final LLM payloads.

Can I view context engine data and memory in an ongoing agent trace?▼

Yes, you can view context engine data and memory. The tool inspects messages, tools, memory, events, and runtime context across both completed and partial execution traces.

How do I start recording agent steps and tool calls without configuration?▼

To start recording agent steps and tool calls without configuration, use this zero-configuration local dev tool. It automatically stores JSON snapshots under a specific directory for CLI navigation.

Where are agent trace snapshots stored for local debugging?▼

Agent trace snapshots are stored as JSON files under the .agent-tracing directory. The CLI exposes commands to navigate and inspect these completed and partial execution traces.

Related Skills

Explore More Software Engineering Skills→
tylerjrbuelltylerjrbuell
21

observability-instrumentation

Configure @reactive-agents observability with verbosity levels, live streaming, JSONL export, model I/O logging, and audit trails for agent execution.

Community
Intermediate
OpenGGFOpenGGF
6

s1-trace-replay

Compare Sonic 1 engine traces against recorded reference data to identify physics divergences.

Official
Advanced
duwenjiduwenji

agent-tracing

Inspect JSON execution snapshots and step-level traces from .agent-tracing.

Community
Advanced
Lobbi-DocsLobbi-Docs
18

FastAPI Observability

Implement structured logging, Prometheus metrics, and OpenTelemetry tracing for FastAPI applications.

Official
Advanced